Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    time, solution, cleaning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     multipart
    0.43
     wohl
    0.42
     aes
    0.40
     issued
    0.40
     attractiveness
    0.38
     limes
    0.38
     likely
    0.38
     perfe
    0.38
     aant
    0.38
    राधिक
    0.38
    POSITIVE LOGITS
    то
    0.47
     limpieza
    0.45
    tos
    0.43
    Unt
    0.41
    Samuel
    0.41
     Mu
    0.41
    Mu
    0.40
    toto
    0.39
    жно
    0.39
     kı
    0.39
    Act Density 0.001%

    No Known Activations